Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    places and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     These
    0.51
     Use
    0.51
     The
    0.49
     because
    0.49
     och
    0.49
     Because
    0.49
     This
    0.48
     You
    0.47
     B
    0.46
     or
    0.45
    POSITIVE LOGITS
    高质量
    0.55
     демокра
    0.55
     unrelenting
    0.55
     приорите
    0.54
     unrival
    0.50
    amı
    0.50
     unparalleled
    0.50
     unapolog
    0.50
     спосо
    0.49
     unwavering
    0.49
    Act Density 0.011%

    No Known Activations